Copertina

Invariance-powered Trustworthy Defense via Remove Then Restore

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fu, Xiaowei, Zhou, Yuhang, Ma, Lina, Zhang, Lei
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense
di: Ma, Lina, et al.
Pubblicazione: (2025)

Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks
di: Zhang, Lei, et al.
Pubblicazione: (2024)

Adversarial Defense in Vision-Language Models: An Overview
di: Fu, Xiaowei, et al.
Pubblicazione: (2026)

Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal
di: Liao, Rongxin, et al.
Pubblicazione: (2025)

Proxy Robustness in Vision Language Models is Effortlessly Transferable
di: Fu, Xiaowei, et al.
Pubblicazione: (2026)

Defense against Unauthorized Distillation in Image Restoration via Feature Space Perturbation
di: Hu, Han, et al.
Pubblicazione: (2025)

Restorer: Removing Multi-Degradation with All-Axis Attention and Prompt Guidance
di: Mao, Jiawei, et al.
Pubblicazione: (2024)

InstructRestore: Region-Customized Image Restoration with Human Instructions
di: Liu, Shuaizheng, et al.
Pubblicazione: (2025)

Exploring Representation Invariance in Finetuning
di: Zu, Wenqiang, et al.
Pubblicazione: (2025)

Improving Image Restoration through Removing Degradations in Textual Representations
di: Lin, Jingbo, et al.
Pubblicazione: (2023)

RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement
di: Zhu, Libo, et al.
Pubblicazione: (2025)

Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start
di: Liu, Fuyang, et al.
Pubblicazione: (2025)

Unifying Physically-Informed Weather Priors in A Single Model for Image Restoration Across Multiple Adverse Weather Conditions
di: Xu, Jiaqi, et al.
Pubblicazione: (2026)

Debiased Dual-Invariant Defense for Adversarially Robust Person Re-Identification
di: Zhou, Yuhang, et al.
Pubblicazione: (2025)

Enhancing Trustworthy GUI Grounding via Self-Critiqued Reinforcement Learning
di: Zhang, Shaojie, et al.
Pubblicazione: (2025)

Fragile by Design: On the Limits of Adversarial Defenses in Personalized Generation
di: Chen, Zhen, et al.
Pubblicazione: (2025)

Learning to Restore Multi-Degraded Images via Ingredient Decoupling and Task-Aware Path Adaptation
di: Gao, Hu, et al.
Pubblicazione: (2025)

Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm
di: Huang, Fuxiang, et al.
Pubblicazione: (2025)

Physically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolution
di: Gao, Hu, et al.
Pubblicazione: (2025)

RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning
di: Guo, Zipeng, et al.
Pubblicazione: (2025)

Decouple to Reconstruct: High Quality UHD Restoration via Active Feature Disentanglement and Reversible Fusion
di: Liu, Yidi, et al.
Pubblicazione: (2025)

LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference-guided Diffusion
di: Xue, Clara, et al.
Pubblicazione: (2026)

Invariance Principle Meets Vicinal Risk Minimization
di: Zhu, Yaoyao, et al.
Pubblicazione: (2024)

Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement
di: Liu, Yidi, et al.
Pubblicazione: (2025)

An Open-World, Diverse, Cross-Spatial-Temporal Benchmark for Dynamic Wild Person Re-Identification
di: Zhang, Lei, et al.
Pubblicazione: (2024)

Artifact Removal and Image Restoration in AFM:A Structured Mask-Guided Directional Inpainting Approach
di: Zhang, Juntao, et al.
Pubblicazione: (2026)

Robust Low-light Scene Restoration via Illumination Transition
di: Li, Ze, et al.
Pubblicazione: (2025)

Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback
di: Lu, Jianglin, et al.
Pubblicazione: (2025)

It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal
di: Qu, Lishen, et al.
Pubblicazione: (2026)

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
di: Chen, Beitao, et al.
Pubblicazione: (2025)

DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering
di: Qiao, Yiran, et al.
Pubblicazione: (2026)

Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models
di: Xu, Jiaqi, et al.
Pubblicazione: (2024)

Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection
di: Yu, Yuyang, et al.
Pubblicazione: (2025)

WeatherRemover: All-in-one Adverse Weather Removal with Multi-scale Feature Map Compression
di: Qu, Weikai, et al.
Pubblicazione: (2026)

Towards Trustworthy Dataset Distillation
di: Ma, Shijie, et al.
Pubblicazione: (2023)

InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention
di: Zhang, Howard, et al.
Pubblicazione: (2024)

DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal
di: Zhou, Ziyang, et al.
Pubblicazione: (2023)

UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity
di: Lin, Jingbo, et al.
Pubblicazione: (2024)

High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer
di: Li, Mingxian, et al.
Pubblicazione: (2024)

DiffuMural: Restoring Dunhuang Murals with Multi-scale Diffusion
di: Han, Puyu, et al.
Pubblicazione: (2025)